What is publish-skills?

A publishing tool for copying personal Claude skills to a GitHub repository, where files can be shared and tracked over time. It can also show proposed changes before publishing.

Use it to publish your skills, compare local skills with the repository, preview changes, or skip the pre-publish audit when appropriate.

It avoids manually gathering skill files and checking what changed since the last publication. Preview and diff modes help you inspect the result before committing or pushing it.

publish-skills — Skill for Claude Code by mostafa-drz

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add mostafa-drz/claude-skills --skill publish-skills

Clone the repo

git clone --depth 1 https://github.com/mostafa-drz/claude-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/publish-skills/github.svg)](https://agentmods.dev/skills/mostafa-drz/claude-skills/publish-skills)

Your own site

<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/publish-skills"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/publish-skills/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/publish-skills"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/publish-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,140 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.03140
Opus 5	$0.00023	$0.01570
Sonnet 5	$0.00009	$0.00628
Haiku 4.5	$0.00005	$0.00314

Measured today against content hash f3ebc26a8206, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade D, and why

publish-skills scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

_On startup, use the Glob tool to find `~/.claude/skills/*/SKILL.md` to count skills, and read preferences (above) to extract repo-path and last-published._

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf {repo-path}/code/{skill-name}

code/publish-skills/SKILL.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish Skills

Publish personal Claude skills to a GitHub repository for sharing and versioning.

Preferences

Read ~/.claude/skills/publish-skills/preferences.md using the Read tool. If not found, no preferences are set.

Context

On startup, use the Glob tool to find ~/.claude/skills/*/SKILL.md to count skills, and read preferences (above) to extract repo-path and last-published.

Command routing

Check $ARGUMENTS:

help → display help then stop
config → interactive setup then stop
reset → delete ~/.claude/skills/publish-skills/preferences.md, confirm, stop
--preview → show what would be published, don't commit/push
--diff → show diff between local skills and published repo
--skip-audit → publish without running pre-publish audit checks
anything else (including empty) → publish

Help

Publish Skills — Share Claude skills via GitHub

Usage:
  /publish-skills                    Publish all skills to GitHub repo
  /publish-skills --preview          Show what would change without publishing
  /publish-skills --diff             Show diff between local and published
  /publish-skills --skip-audit       Publish without pre-publish audit checks
  /publish-skills config             Set repo path and GitHub remote
  /publish-skills reset              Clear preferences
  /publish-skills help               This help

What it does:
  1. Copies skill files to the publish repo (excludes preferences, audit logs)
  2. Generates a README.md catalog from skill descriptions
  3. Commits changes with a summary message
  4. Pushes to GitHub

What gets published:
  - SKILLS_GUIDE.md (design guide)
  - Each skill's SKILL.md
  - Each skill's reference/ and examples/ directories
  - Auto-generated README.md catalog

What stays private:
  - preferences.md files (user-specific config)
  - last-audit.md (audit logs)
  - Any file matching .gitignore patterns

Current preferences:
  (shown above under Preferences)

Read the full file on GitHub · 413 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed · +3 lines · +45 tokens per session f3ebc26a8206
12d ago First seen · 410 lines · 0 tokens per session scan D ee27c076c5c7

Subscribe to this mod's changes

publish-skills is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 3,140 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Git and workflow ai-tools automation claude claude-skills developer-tools

git-pushing

Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.

mhattingpete/claude-skills-marketplace · 70 tokens

iterate

Diverge-converge workflow: spin up N agents on isolated worktrees, each exploring a different approach to the same problem. Compare results side-by-side (with optional preview ports), pick a winner, merge it back. Use when the user says /iterate, 'try multiple approaches', 'explore different directions', or wants to…

SZoloth/skill-pack · 73 tokens

publish-skills